From 6a6d3137f28450e2c257ae4f35b560cb8282ce12 Mon Sep 17 00:00:00 2001
From: "yusuke.shinyama.dummy"
 <yusuke.shinyama.dummy@1aa58f4a-7d42-0410-adbc-911cccaed67c>
Date: Sun, 29 Jun 2008 14:29:36 +0000
Subject: [PATCH] documentation.

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@39 1aa58f4a-7d42-0410-adbc-911cccaed67c
---
 README.html         | 17 ++++++++++-------
 pdflib/pdfparser.py |  1 +
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/README.html b/README.html
index a5f4779..02dc189 100644
--- a/README.html
+++ b/README.html
@@ -11,7 +11,7 @@ blockquote { background: #eeeeee; }
 <h1>PDFMiner</h1>
 <div align=right class=lastmod>
 <!-- hhmts start -->
-Last Modified: Sun Jun 29 17:53:42 JST 2008
+Last Modified: Sun Jun 29 19:58:40 JST 2008
 <!-- hhmts end -->
 </div>
 
@@ -20,16 +20,18 @@ Last Modified: Sun Jun 29 17:53:42 JST 2008
 <h2>What's It?</h2>
 <p>
 PDFMiner is a suite of programs that aims to help
-extracting or analyzing text data from PDF documents.
+analyzing text data from PDF documents.
+It includes a PDF parser, a PDF interpreter 
+(though only rendering text is supported for now),
+and a couple of nice tools to extract texts.
 Unlike other PDF-related tools, it allows to obtain
 the exact location of texts in a page, as well as 
 other layout information such as font size or font name,
 which could be useful for analyzing the document.
-It can be also used as a basis for a full-fledged PDF interpreter.
 <p>
 <strong>Features:</strong>
 <ul>
-<li> Written entirely in Python. 
+<li> Written entirely in Python. (for version 2.4 or newer)
 <li> Roughly supports up to PDF-1.7 specification.
 <li> Supports non-ASCII languages and vertical writing scripts.
 <li> Supports various font types (Type1, TrueType, Type3, and CID).
@@ -217,9 +219,10 @@ no stream header is displayed for the ease of saving it to a file.
 <hr noshade>
 <h2>Changes</h2>
 <ul>
-<li> 2007/04/29: Bugfix for Win32. Thanks to Chris Clark.
-<li> 2007/04/27: Basic encryption and LZW decoding support added.
-<li> 2007/01/07: Several bugfixes. Thanks to Nick Fabry for his contribution.
+<li> 2008/06/29: Added HTML output. Reorganized the directory structure.
+<li> 2008/04/29: Bugfix for Win32. Thanks to Chris Clark.
+<li> 2008/04/27: Basic encryption and LZW decoding support added.
+<li> 2008/01/07: Several bugfixes. Thanks to Nick Fabry for his contribution.
 <li> 2007/12/31: Initial release.
 <li> 2004/12/24: Start writing the code out of boredom...
 </ul>
diff --git a/pdflib/pdfparser.py b/pdflib/pdfparser.py
index d73d5de..494b6db 100755
--- a/pdflib/pdfparser.py
+++ b/pdflib/pdfparser.py
@@ -767,6 +767,7 @@ class PDFParser(PSStackParser):
         if not m: continue
         (objid, genno) = m.groups()
         offsets[int(objid)] = (0, pos, 'f')
+      if not offsets: raise
       xref.offsets = offsets
       xref.objid0 = min(offsets.iterkeys())
       xref.objid1 = max(offsets.iterkeys())